ppt - University of Illinois at Urbana

Download Report

Transcript ppt - University of Illinois at Urbana

Basic IR Concepts & Techniques

ChengXiang Zhai

Department of Computer Science University of Illinois, Urbana-Champaign

Text Information Systems Applications

Access

Select

information

Mining

Create Knowledge

Organization

Add

Structure/Annotations 2

Two Modes of Information Access: Pull vs. Push

Pull Mode

Users take initiative and “pull” relevant information out from a text information system (TIS)

Works well when a user has an ad hoc information need

Push Mode

Systems take initiative and “push” relevant information to users

Works well when a user has a stable information need or the system has good knowledge about a user’s need

3

Pull Mode: Querying vs. Browsing

Querying

A user enters a (keyword) query, and the system returns relevant documents

Works well when the user knows exactly what keywords to use

Browsing

The system organizes information with structures, and a user navigates into relevant information by following a path enabled by the structures

Works well when the user wants to explore information or doesn’t know what keywords to use, or can’t conveniently enter a query (e.g., with a smartphone)

4

Information Seeking as Sightseeing

Sightseeing: Know address of an attraction?

Yes: take a taxi and go directly to the site

No: walk around or take a taxi to a nearby place then walk around

Information seeking: Know exactly what you want to find?

Yes: use the right keywords as a query and find the information directly

No: browse the information space or start with a rough query and then browse Querying is faster, but browsing is useful when querying fails or a user wants to explore

5

Text Mining: Two Different Views

Data Mining View: Explore patterns in textual data

Find latent topics

Find topical trends

Find outliers and other hidden patterns

Natural Language Processing View: Make inferences based on partial understanding of natural language text

Information extraction

Knowledge representation + inferences

Often mixed in practice

6

Applications of Text Mining

Direct applications

– Discovery-driven (Bioinformatics, Business Intelligence, etc): We have specific questions; how can we exploit data mining to answer the questions?

– Data-driven (WWW, literature, email, customer reviews, etc): We have a lot of data; what can we do with it? •

Indirect applications

– Assist information access (e.g., discover latent topics to better summarize search results) – Assist information organization (e.g., discover hidden structures) 7

IR Topics (Broader View): Text Information Systems (TIS)

Retrieval Applications

Information Access

Summarization Filtering Search

Information Organization

Visualization Clustering Extraction Categorization Topic Analysis Mining Applications

Knowledge Acquisition Natural Language Content Analysis Text 8

Elements of TIS:

Natural Language Content Analysis

Natural Language Processing (NLP) is the foundation of TIS

– Enable understanding of meaning of text – Provide semantic representation of text for TIS •

Current NLP techniques mostly rely on statistical machine learning enhanced with limited linguistic knowledge

– Shallow techniques are robust, but deeper semantic analysis is only feasible for very limited domain • •

Some TIS capabilities require deeper NLP than others Most text information systems use very shallow NLP (“bag of words” representation)

9

Elements of TIS: Text Access

Search:

take a user’s query and return relevant documents • •

Filtering/Recommendation:

monitor an incoming stream and recommend to users relevant items (or discard non-relevant ones) •

Categorization:

classify a text object into one of the predefined categories

Summarization:

take one or multiple text documents, and generate a concise summary of the essential content 10

Elements of TIS: Text Mining

• • •

Topic Analysis:

take a set of documents, extract and analyze topics in them •

Information Extraction:

extract entities, relations of entities or other “knowledge nuggets” from text

Clustering:

discover groups of similar text objects (terms, sentences, documents, …)

Visualization:

visually display patterns in text data 11

IR Topics (narrow view)

docs

SEARCHING

Doc Rep

Query Rep

query 6. User interface (browsing) User 1. Evaluation results Feedback 7. Feedback/Learning

QUERY MODIFICATION LEARNING

Our focus: 1, 2, 7

12

Typical TR System Architecture

docs query Tokenizer Feedback Doc Rep (Index) Indexer

Query Rep Index

Scorer judgments User results

13

Tokenization

Normalize lexical units: Words with similar meanings should be mapped to the same indexing term

Stemming: Mapping all inflectional forms of words to the same root form, e.g.

computer -> compute

computation -> compute

computing -> compute

Some languages (e.g., Chinese) pose challenges in word segmentation

14

Indexing

Indexing = Convert documents to data structures that enable fast search

Inverted index is the dominating indexing method (used by all search engines): basic idea is to enable quick look up of all the documents containing a particular term

Other indices (e.g., document index) may be needed for feedback

15

How to Design a Ranking Function?

• • • • •

Query q = q 1 ,…,q m, where q i

V Document d = d 1 ,…,d n, where d i

V Ranking function: f(q, d)



A good ranking function should rank relevant documents on top of non-relevant ones

Key challenge: how to measure the likelihood that document d is relevant to query q?

Retrieval Model = formalization of relevance (give a computational definition of relevance)

16

Many Different Retrieval Models

Similarity-based models:

a document that is more similar to a query is assumed to be more likely relevant to the query

relevance (d,q) = similarity (d,q)

e.g., Vector Space Model

Probabilistic models (language models):

compute the probability that a given document is relevant to a query based on a probabilistic model

relevance(d,q) = p(R=1|d,q), where R

{0,1} is a binary random variable

E.g., Query Likelihood

17

Relevance Feedback

Users make explicit relevance judgments on the initial results (judgments are reliable, but users don’t want to make extra effort) Query

Retrieval Engine

Results: d 1 3.5

d 2 … 2.4

d k ...

0.5

Updated query

User

Document collection Feedback

Judgments: d 1 + d 2 d 3 + … d k ...

18

Pseudo/Blind/Automatic Feedback

Top-k initial results are simply assumed to be relevant (judgments aren’t reliable, but no user activity is required) Query

Retrieval Engine

Results: d 1 3.5

d 2 … 2.4

d k ...

0.5

Updated query Document collection Feedback

Judgments: d 1 + d 2 d 3 + … + d k ...

-

top 10 assumed relevant

19

Implicit Feedback

User-clicked docs are assumed to be relevant; skipped ones non-relevant (judgments aren’t completely reliable, but no extra effort from users) Query

Retrieval Engine

Results: d 1 3.5

d 2 … 2.4

d k ...

0.5

Updated query

User

Document collection Feedback Clickthroughs

: d 1 + d 2 d 3 + … d k ...

20

Evaluation: Two Different Reasons

• •

Reason 1: So that we can assess how useful an IR system/technology would be (for an application)

Measures should reflect the utility to users in a real application

Usually done through user studies (interactive IR evaluation) Reason 2: So that we can compare different systems and methods (to advance the state of the art)

Measures only need to be correlated with the utility to actual users, thus don’t have to accurately reflect the exact utility to users

Usually done through test collections (test set IR evaluation)

21

What to Measure?

Effectiveness/Accuracy: how accurate are the search results?

Measuring a system’s ability of ranking relevant docucments on top of non-relevant ones

Efficiency: how quickly can a user get the results? How much computing resources are needed to answer a query?

Measuring space and time overhead

Usability: How useful is the system for real user tasks?

Doing user studies

22

The Cranfield Evaluation Methodology

A methodology for laboratory testing of system components developed in 1960s

Idea: Build reusable test collections & define measures

A sample collection of documents (simulate real document collection)

A sample set of queries/topics (simulate user queries)

Relevance judgments (ideally made by users who formulated the queries)

Ideal ranked list

Measures to quantify how well a system’s result matches the ideal ranked list

A test collection can then be reused many times to compare different systems

23

What You Should Know

• • •

Information access modes: pull vs. push Pull mode: querying vs. browsing Basic elements of TIS:

search, filtering/recommendation, categorization, summarization

topic analysis, information extraction, clustering, visualization

Know the terms of the major concepts and techniques (e.g., query, document, retrieval model, feedback, evaluation, inverted index, etc)

24